Name: 2x DigiGradients Lite
Author: SaurusX

Attempts to remove the damages done by color banding. For this model, I downscaled all of the HR images to make their pixel size closer to 1000x1000 using the Box filter and then downscaled them again by 50% using the Point filter. Afterwards, I applied 64-bit color banding to every image in the dataset.

Comparisons with other models: https://imgsli.com/NTA1NTk

Bandage Smooth

Debandurh_FS Ultra-lite

N64 textures use a color depth of 5-bits per channel, this model attempts to clean them, restoring smooth gradients in textures

N64clean

Takes composite/RF/VHS NES footage and attempts to restore it to RGB quality. Assumes footage has been properly deinterlaced via field duplication from 240p to 480p/720p/etc. Note that:

* All footage was captured in 240p/480p/720p NTSC.
* RGB footage was captured via an AV Famicom with the RGB Blaster via the Retrotink 2x or GBS Control.
* The model was trained exclusively on individual frames, so it can't fix things like dropouts.
* The even and odd fields of NES composite tend to be a bit...different from each other, so there will be some jitter at 60fps.
* I don't have access to an NES Toploader, so I wouldn't expect it to fix the jailbars very well.

Revision History:

* 1.5.0 (06/29/2025): Applied additional augmentations to reduce overfitting. Also added a small amount of 720p training data.
* 1.0.0 (11/03/2024): Initial release.

NES Composite to RGB

Ani4K is a 2x model for creating natural-looking 2K and 4K upscales of modern anime. The model places emphasis on depth of field and blur effect retention, which are extremely common in modern anime and something that many anime models struggle with. In addition, Ani4K is trained for strong detail retention, WEB/BD compression clean-up, and producing pleasing lineart. 

More info on the Github page: https://github.com/Sirosky/Sirosky-Upscaling-Models.

Blur Retention Comparisons (including vs. xinntao's 2x paper model): https://imgsli.com/MTg2NTg5/4/5

General Comparisons: https://imgsli.com/MTg2ODI2

Ani4K

## Ani4K v2  

 Ani4K v2, as the successor to the original Ani4K, retains its predecessor's fantastic detail retention, depth of field preservation and faithfulness to the original source. As the name suggests, the model is targeted at modern anime, ranging from high-quality Bluray to crappy WEB releases, for upscaling either to 2K or 4K.

An **UltraCompact** version of the model is available on the [Github release](https://github.com/Sirosky/Upscale-Hub/releases/tag/Ani4K-v2). The UltraCompact version is faster, without a perceptual hit to quality in most cases.

📌 [More comparisons](https://slow.pics/c/1HykdyT5)

****

**FAQ**

- *How does v2 differ from v1?* I'm so glad you asked! A shortcoming of the v1 models is that the model really struggled on sources which were poorly mastered. This is unfortunately still very common even with modern anime. v2 is far more capable of dealing with such sources. 
- *How does Ani4K v2 differ from JaNai v3? Which one should I pick?* JaNai v3 is a fantastic model, and shares many of the fundamental training objectives behind Ani4K (DOF preservation, faithfulness, etc.). I'd say that the primary difference is one of training philosophy-- JaNai seeks to render the source as if it was originally mastered in 4K, whereas Ani4K seeks to produce an upscale that is as close as possible to the source (while cleaning up any issues). Long story short, test both models and see which you prefer.
- *What model versions are there?* Ani4K comes in Compact and UltraCompact flavors. Compact is of course a standard option. UltraCompact provides a noticeable performance uplift, without too much impact on quality. I ultimately did not train a SuperUltraCompact variant as I felt the hit to the model quality was far too significant.

Ani4VK v2 Compact

## AniSD Suite (15 models)

**Scale:** 2x (1x for AniSD DB)  
**Architecture:** SPAN / Compact / SwinIR Small / CRAFT / DAT2  / RPLKSR

**Dataset:** Anime frames. Credits to @.kuronoe. and @pwnsweet (EVA dataset) for their contributions to the dataset!  
**Dataset Size:** ~7,000 - ~13,000  

AniSD is a suite of 15 (as of time of writing) specialized SISR models trained to restore and upscale standard definition digital anime from ~2000s and onwards, including both both WEB and DVD releases. Faithfulness to the source and natural-looking output are the guiding principles behind the training of the AniSD models. This means avoiding oversharpened output (which can look especially absurd on standard definition sources), minimizing upscaling artifacts, retaining the natural detail of the source and of course, fixing the standard range of issues found in many DVD/WEB release (chroma issues, compression, haloing/ringing, blur, dotcrawl, banding etc.). Refer to the infographic above for a quick breakdown of the available models, and refer to the [Github release](https://github.com/Sirosky/Upscale-Hub/releases/tag/AniSD-RealPLKSR) for further information.

AniSD Suite (Multiple Models)

Purpose: Anime/Pretrained

A 2x Ultra Lite model coming in under 8MB. Trained with over 15 sets of LRs ranging in a wide amount of issues. Handles Rainbows, Dot Crawl, MPEG/H.264 Compression, and may even assist in removing halos, and fixing blurriness in certain cases. This is my first public model for everyone. Best when used on old anime that is grainy. I can't say what anime it's best suited for as I have tried multiple series, and have found it does a good job on most all the tests. I wouldn't say use this for Western Animation, but it may work. I have done a few tests that I have shown in the upscale results, but that was chained with other models to achieve such a result. This model is meant to retain the more natural look of a series. There is a color shift on the end result, not drastic, but still noticable. I figure you should fix any color issues in post that way to give a more polished upscale. Big thanks to @SaurusX for the model name, and just helping out in general with anything.

AnimeClassics UltraLite

Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K. 

The aim of these models is to address scaling, blur, oversharpening, and compression artifacts while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai

The development of the V3 models spanned over seven months, during which over 100 release candidate models were trained and meticulously refined. The V3 models introduce several improvements compared to V2, including:

More faithful appearance to original source
Improved handling of oversharpening artifacts, ringing, aliasing
Better at preserving intentional blur in scenes using depth of field
More accurate line colors, darkness, and thickness
Better preservation of soft shadow edges

Overall, the V3 models yield significantly more natural and faithful results compared to the V2 models.test

AnimeJaNai_HD_V3_Compact

Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K.

The aim of these models is to address scaling, blur, oversharpening, and compression artifacts while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai

The development of the V3 models spanned over seven months, during which over 100 release candidate models were trained and meticulously refined. The V3 models introduce several improvements compared to V2, including:

More faithful appearance to original source Improved handling of oversharpening artifacts, ringing, aliasing Better at preserving intentional blur in scenes using depth of field More accurate line colors, darkness, and thickness Better preservation of soft shadow edges

Overall, the V3 models yield significantly more natural and faithful results compared to the V2 models.

AnimeJaNai_HD_V3_SuperUltraCompact

AnimeJaNai_HD_V3_UltraCompact

Realtime 2x model intended for high or medium quality 1080p anime with an emphasis on correcting the inherit blurriness of anime while preserving details and colors. Not suitable for artifact-heavy or highly compressed content as it will just sharpen artifacts. Also works with SD anime by running the model twice. Can be set up to run with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai

Minimum of RTX 3080 is recommended for running UltraCompact model on 1080p in realtime; RTX 4090 is required to run Compact on 1080p in realtime. SuperUltraCompact should run in realtime on 1080p on some lower cards. The compact model is recommended on SD content. 

Samples: https://imgsli.com/MTUxMDYx \
Comparisons to Anime4K + other compact models and upscalers: https://imgsli.com/MTUxMjY4

AnimeJaNai Standard v1 Compact

AnimeJaNai Standard v1 SuperUltraCompact

AnimeJaNai Standard v1 UltraCompact

AnimeJaNai Strong v1 Compact

I used frames from 5 episodes from the PAL DVD sets with differing quality levels against the German Blu-rays in order to reverse engineer an AstroRes model. Detail enhancement is very high though it helps to have a good quality source (of course). The model will remove MPEG-2, some halos, and PAL-conversion artifacts like image trails and faded lines to great effect. Temporal stability is quite good.

AstroManLite

Purpose: To recreate the upscale process used in the He-Man German Blu-ray release.

A followup to my previous AstroManLite model. The primary focus is on detail preservation and enhancement of decent DVD material instead of artifact repair. I eliminated the attempt to remove temporal artifacts from the He-Man DVDs as it proved detrimental to the final results. It will, however, remove MPEG-2 artifacts to great effect.

AstroManPlus 262k

Using the Kineko 4K scan the hope was to clean up the Funi DVD releases and upscale to something comparable. This model degrains the series pretty damn well, but what's revealed beneath is a lot of moving noise that's probably best dealt with in pre- or post- with a video editor like AVISynth. So while the model is remarkably temporally stable, the DBZ sources certainly aren't. The movies look really nice when upscaled with raw input, though.

2x_DBZScanLite

Purpose: Digital Animation

A very focused model meant for upscaling the TMNT 2003 DVDs. Degradations were added via AVISynth in order to match the video on the TMNT 2003 DVDs to correct the source problems. Problems corrected include aliased red chroma, chroma vertical blur, bad deinterlacing, banding, compression "grain", and poor animation line detail. The AVS scripts for the LR's were run through HCEnc to get authentic low bit rate MPEG-2 artifacts for fixing. By design, the final model gives a very digital-looking result and does not do a good job of retaining textures as the style of TMNT 2003 is all flats and gradients.

DigiGradients Lite

Purpose: Digital Animation

Meant as a versatile model for upscaling high detail digital anime and cartoons. Has debanding, MPEG-2 correction, and halo reduction. Trained to handle both 4:3 and 16:9 DVD material with equal efficacy. Will retain a lot of textures except for the really high freq stuff.

Digitoon Lite

Purpose: Upscale Evangelion episode 16

An ESRGAN Lite model trained on the dataset provided by pwnsweet. I had to make the adjustment of transfering average brightness and contrast from the LR's to the HR's to avoid flashing in the final model. Otherwise the dataset is as provided.

https://imgsli.com/MjM5Njk5

Eva16Lite 201k

Purpose: Upscale Evangelion episode 16

An earlier iteration of my other ESRGAN lite model. After some closer examination at the video output of the other model I think this one is also worth considering. For being at such an early stage, this model is extremely stable, which makes me think the other model may be exhibiting some overfitting issues. Definitely worth a look.

Eva16Lite 64k

Meant to preserve original 4:3 framing of G&F while upscaling. Trained to handle all seven seasons, which drastically differ in quality. Fixes include rainbowing, dot-crawl, halos, general noise, and of course MPEG-2 artifacts. It should be generally flexible in dealing with different degrees of those artifacts, but as always the cleaner the source the better. The model could be useful with other shows from the '80s and '90s with ugly video sources. Maybe.

2x_Garfield1_308k

In addition to removing the vertical blur, the model upscales, sharpens and will remove MPEG-2 artifacting and a small amount of rainbowing and dot crawl. Another series afflicted with the vertical blur is Avatar the Last Airbender, which can be repaired by this model. The video fed into the model MUST be 540 vertical for the deblur to work properly.

SwatKats

PBRify Github: https://github.com/Kim2091/PBRify_Remix

Release Link: https://github.com/Kim2091/Kim2091-Models/releases/tag/4x-PBRify_RPLKSRd_V3

This update brings a new upscaling model, 4x-PBRify_RPLKSRd_V3. This model is roughly 8x faster than the current DAT2 model, while being *higher quality*. It produces far more natural detail, resolves lines and edges more smoothly, and cleans up compression artifacts better.

As a result of those improvements, PBR is also much improved. It tends to be clearer with less defined artifacts. 

However, this model is currently **only compatible with ComfyUI**. chaiNNer has not yet been updated to support this architecture.

[More Comparisons](https://imgsli.com/Mjk5NjQ5)

Architecture	ESRGAN
Scale	2x
Size	32nf12nb
Color Mode	RGB
License	CC-BY-NC-SA-4.0 Private use Distribution Modifications Credit required Same License State Changes No Liability & Warranty Disclaimer
Date	2022-08-24
Dataset	Images from The Batman (series) HD WEB-DL.
Training iterations	486000
Training batch size	4
Training HR size	128

DigiGradients Lite

Similar Models